acrescentar

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and discharges much of it: it discloses the 504/timeout behavior right after page creation, the `onde` placement semantics (fim/inicio/#id), how attachments are cited (anexo:N), and that titles must travel in the parameter rather than the body. It does not cover permissions or what the call returns, but for a no-annotation tool this is unusually informative.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose sentence is buried behind a generic workflow preamble (read the spec, read the page, imitate neighbors, report warnings) that reads more like server-level instructions than tool-specific content. Every line does convey something useful, but front-loading the actual 'what this does' would improve scannability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema and no annotations exist, so the description must stand alone, and it covers placement, attachments, error timing, and authoring style. Missing pieces are the return value (does it return new block ids?) and the expected `pagina_id` identifier format.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate and largely does: it enumerates the `onde` values and default, explains the `anexos` collection and its anexo:N citation convention, and states where the title belongs. `pagina_id` and `conteudo` are left only implicitly defined, which is the remaining gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The sentence 'Acrescenta ONMD numa página que já existe' states a specific verb (append/insert content) and resource (an existing OneNote page), and the `onde` parameter clarifies the placement model. It never names the siblings it overlaps with (inserir, editar, criar_pagina), so an agent must infer the boundary with those tools, which keeps it below 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Strong procedural guidance: read ler_spec before writing, read ler_pagina before editing, make the smallest possible edit, re-read after structural changes, and wait a few seconds after page creation due to 504s. What is missing is an explicit when-not/alternative clause naming inserir or editar, which is the one thing that would push this to 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.